paper-with-me

홈 › Papers

PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models

2025-07-25 · Tarek Gasmi, Ramzi Guesmi, Mootez Aloui, Jihene Bennaceur arxiv

Static benchmarks fail to capture LLM vulnerabilities emerging through community experimentation in online forums. We present PrompTrend, a system that collects vulnerability data across platforms and evaluates them using multidimensional scoring, with an architecture designed for scalable monitoring. Cross-sectional analysis of 198 vulnerabilities collected from online communities over a five-month period (January-May 2025) and tested on nine commercial models reveals that advanced capabilities correlate with increased vulnerability in some architectures, psychological attacks significantly outperform technical exploits, and platform dynamics shape attack effectiveness with measurable model-specific patterns. The PrompTrend Vulnerability Assessment Framework achieves 78% classification accuracy while revealing limited cross-model transferability, demonstrating that effective LLM security requires comprehensive socio-technical monitoring beyond traditional periodic assessment. Our findings challenge the assumption that capability advancement improves security and establish community-driven psychological manipulation as the dominant threat vector for current language models.

📄 PDF Abstract BibTeX arXiv:2507.19185

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On managing vulnerabilities in AI/ML systems

2021-01-22 · Jonathan M. Spring, April Galyardt, Allen D. Householder, Nathan VanHoudnos

This paper explores how the current paradigm of vulnerability management might adapt to include machine learning systems through a thought experiment: what if flaws in machine learning (ML) were assigned Common Vulnerabi…

BIG-bench Machine LearningManagement

CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software

2021-07-19 · Guru Prasad Bhandari, Amara Naseer, Leon Moonen

Data-driven research on the automated discovery and repair of security vulnerabilities in source code requires comprehensive datasets of real-life vulnerable code and their fixes. To assist in such research, we propose a…

severity prediction

MoreFixes: A Large-Scale Dataset of CVE Fix Commits Mined through Enhanced Repository Discovery

2024-07-10 · Promise 2024 7 · Jafar Akhoundali, Sajad Rahim Nouri, Kristian Rietveld, and Olga Gadyatskaya

Vulnerability datasets have become an important instrument in software security research, being used to develop automated, machine learning-based vulnerability detection and patching approaches. Yet, any limitations of t…

Vulnerability Detection

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers

2022-10-20 · Guangsheng Zhang, Bo Liu, Huan Tian, Tianqing Zhu 외

As a booming research area in the past decade, deep learning technologies have been driven by big data collected and processed on an unprecedented scale. However, privacy concerns arise due to the potential leakage of se…

AttributeDeep Learning

LLM-based Vulnerability Discovery through the Lens of Code Metrics

2025-09-23 · Felix Weissberg, Lukas Pirch, Erik Imgrund, Jonas Möller 외 arxiv

Large language models (LLMs) excel in many tasks of software engineering, yet progress in leveraging them for vulnerability discovery has stalled in recent years. To understand this phenomenon, we investigate LLMs throug…